IEEE Journal of Biomedical and Health Informatics

Background: Attention-Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder characterized by persistent symptoms of inattention, hyperactivity, and impulsivity that significantly affect cognitive, academic, and social functioning. Although electroencephalography (EEG) has emerged as a promising non-invasive tool for identifying objective neurophysiological biomarkers of ADHD because of its high temporal resolution and cost-effectiveness, many existing machine learning studies rely on single-domain EEG features, which may not adequately capture the complex functional organization of the brain. Methods: This study proposes a subject-level EEG classification framework that integrates three complementary feature domains: spectral characteristics, weighted Phase Lag Index (wPLI)-based functional connectivity, and topological descriptors derived from persistent homology. EEG recordings from 121 subjects were preprocessed and segmented into overlapping windows for feature extraction. Window-level features were aggregated to generate subject-level representations. Recursive Feature Elimination (RFE) was employed to select the 110 most informative features from an initial set of 1,043 descriptors. Five machine learning classifiers, including Support Vector Machine (SVM), Random Forest, XGBoost, CatBoost, and Multi-Layer Perceptron (MLP), were evaluated using stratified five-fold cross-validation. An ablation study was further conducted to assess the contribution of each feature domain. Model interpretability was investigated using SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), two widely adopted Explainable Artificial Intelligence techniques for interpreting machine learning models. Results: Among the evaluated classifiers, the SVM achieved the highest classification performance, yielding an accuracy of 80.17%, an F1-score of 80.95%, a balanced accuracy of 80.14%, a receiver operating characteristic area under the curve (ROC-AUC) of 86.72%, and a precision recall area under the curve (PR-AUC) of 87.34%. The ablation study demonstrated that combining spectral, functional connectivity, and topological features consistently outperformed individual feature domains, highlighting the complementary nature of these representations. Explainable AI analyses further identified functional connectivity features as the primary contributors to classification performance while confirming the additional value of spectral and topological descriptors. Conclusions: The proposed framework demonstrates that integrating spectral analysis, functional connectivity, and topological data analysis provides an effective and interpretable approach for subject-level ADHD classification from EEG recordings. The combination of recursive feature selection, multi-domain feature fusion, ablation analysis, and Explainable Artificial Intelligence establishes a transparent and reproducible pipeline that may facilitate the development of reliable EEG-based clinical decision-support systems for ADHD.

Longitudinal clinical cohorts contain heterogeneous progression patterns that are obscured by coarse diagnostic labels. Discovering these latent progression phenotypes requires models that distinguish patients not only by their outcomes, but also by how their clinical trajectories evolve. This paper proposes TRACE, an interpretable temporal phenotyping method that enables the learning of outcome-informed progression phenotypes from longitudinal trajectories. TRACE combines a trajectory- and outcome-aware contrastive objective with a probabilistic predictive phenotype layer, encouraging phenotypes to capture progression structure while remaining predictive of diagnostic state. A dual-attention mechanism further supports interpretation by identifying the visits and clinical variables most associated with each phenotype assignment. TRACE is evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for cognitive disease modeling, showing improved performance in both diagnostic prediction and phenotype discovery compared with other temporal phenotyping baselines. Finally, by allowing the number of phenotypes to exceed the diagnostic labels, TRACE enables discovering additional progression patterns that are not captured by labels defined a priori.

In this work, we investigate the homogeneity of performance in binary classification between the Rotterdam phenotypes and phenotype prediction. For this purpose, a multi-task neural network architecture is designed to improve the prediction accuracy of phenotypes while maintaining the accuracy of binary classification. Using a clinical PCOS dataset which contains unlabeled samples of patients that cannot be attributed to any of the known phenotypes, three models are evaluated: optimized binary Random Forest (RF), six-class weighted class RF, and multi-task neural network (with a common hidden layer and two heads for binary and six-class classifications) optimized by a genetic algorithm. Techniques used for evaluation include ten-fold out-of-fold predictions, paired McNemar tests, bootstrap tests, ablation study, and clustering (Adjusted Rand Index, ARI). Binary RF model reached 90.2% accuracy; however, recall of different phenotypes was significantly unbalanced - from 75.0% of phenotype B to 97.8% of phenotype A. This difference of 22.8 % points was observed (23.3 points) even after excluding phenotype-specific features. While direct phenotype prediction improved recall for common phenotypes, it decreased recall for phenotype B to 43.8% and unclassified cases to 31.5%. Our multi-task model preserved 90.2% binary accuracy and significantly recovered phenotype B recall to 87.5% and unclassified cases to 79.6% (p<0.05). The cluster analysis confirmed the weak correlation between the results and labels (ARI=0.045). The ablation analysis demonstrates that feature selection and class weighting drive this improvement, isolating the specific components responsible for performance gains. We establish that aggregate binary accuracy does not reflect the heterogeneous detection of PCOS phenotypes. Direct phenotype prediction alone redistributes the classification errors, but the multi-task architecture successfully improves the detection of rare phenotypes without compromising binary accuracy. Phenotype-disaggregated evaluations, supported by significance testing and ablation, are essential for clinical classifier research.

In hypertension screening, previously diagnosed cases provide reliable positive labels, whereas individuals without a prior diagnosis comprise both undiagnosed hypertensive and non-hypertensive individuals, creating a canonical positive-unlabeled (PU) learning setting. We propose PU-Boost, a two-stage reliable-sample reconstruction framework that uses only readily obtainable demographic, behavioral, medical-history, and anthropometric variables. During training, only previously diagnosed hypertension cases are treated as labeled positives (P), while all remaining individuals are treated as unlabeled (U); no additional reference labels are supplied to the two-stage reconstruction procedure. Elastic Net first provides a global ranking of P versus U, after which a random forest refines the uncertain region and highly ambiguous observations are rejected. XGBoost is then trained on the reconstructed class-balanced pseudo-labeled sample. In the independent test set, PU-Boost achieved a sensitivity of 0.817 and a balanced accuracy of 0.682, the highest observed values among the compared models. It produced 729 false negatives, 41.1% fewer than standard XGBoost, although specificity decreased to 0.547. SHAP analysis indicated that established hypertension-related features, including age, body mass index, waist circumference, and family history, contributed strongly to model output. PU-Boost therefore provides a statistically motivated framework for reducing missed cases when screening for undiagnosed hypertension under incomplete diagnostic labeling.

Multiview data analysis has become increasingly important for integrating heterogeneous information from multiple data sources. Cooperative learning provides a flexible framework for multiview integration by bridging early and late fusion strategies. However, its use of squared loss makes it sensitive to outliers. In this study, we propose robust cooperative learning based on the soft-IPOD framework. The proposed method introduces an observation-specific outlier absorption vector into the cooperative learning objective, thereby reducing the influence of outlying observations while preserving information sharing across views. The resulting optimization problem can be formulated as a weighted Lasso-type problem using an augmented design matrix and can be naturally extended to more than two data views. Numerical simulations and a real-data application to labor onset prediction demonstrate the predictive performance of the proposed method in the presence of outliers.

Automated triage of whole-slide cervical cytology images remains constrained by the heavy dependence on single-cell bounding boxes or pixel-level annotations, which introduce significant bottlenecks, high expert overhead, and observer variability. To address these challenges, we present a weakly-supervised, detection-free Multiple Instance Learning (MIL) framework powered by a Gated Attention pooling engine that operates exclusively on slide-level predictions. By treating whole-slide images as bags of local instance patches, the dual-branch gated network dynamically assigns non-linear attention weights to highlight isolated dysplastic cells while suppressing benign background and debris, successfully resolving the "needle-in-a-haystack" problem inherent to high-grade lesions. Evaluated across multi-center cohorts including internal datasets (SIPaKMeD, Herlev, and CRIC) and the unannotated, out-of-distribution Mendeley LBC validation cohort processed via an unsupervised marker-controlled watershed pipeline our approach demonstrates robust generalization without requiring dense instance labels. Furthermore, our architectural comparison reveals a key trade-off: lightweight backbones like MobileNetV2 optimize in-distribution multi-center accuracy (90.96% Accuracy, 0.9800 ROC-AUC), whereas higher-capacity models like Xception ensure superior out-of-distribution robustness (80.43% Balanced Accuracy) under domain shifts. Ultimately, this detection-less pipeline provides a scalable and clinically viable solution to automate slide triage and alleviate cytopathologist shortages in resource-constrained environments.

In many natural dynamical systems, tipping points emerge where slowly changing external factors induce shifts from one state to another, known as critical transitions or bifurcations. In epidemic systems, detecting these transitions is important for outbreak preparedness. Various statistical indicators like lag-1 autocorrelation and variance have been employed as early warning signals (EWS) of critical transitions by showing how the dynamics of the system exhibit critical slowing down (CSD) near the transition. More recently, deep learning-based algorithms have been developed that attempt to more accurately detect and classify bifurcations; however, they are limited by the systems simulated in the training dataset, the length of the time series, and have not been rigorously evaluated on real-world epidemic data spanning multiple geographic regions. In this paper, we evaluate existing deep learning-based bifurcation prediction models, on a CDC-curated dataset containing weekly influenza hospital admissions across all fifty U.S. states and the nation as a whole. We develop a pipeline for data preparation, reproduction number (Rt) estimation using the EpyEstim package (a Python implementation of the EpiEstim framework [4]), and bifurcation point identification. We systematically evaluate the models under several windowing strategies, including rolling, expanding, and fixed-length windows, and report accuracy, precision, recall, F1 score, and specificity. Our best-performing configuration (expanding window, length 100) achieves an accuracy of 90.09%, precision of 72.86%, recall of 96.23%, and F1 score of 82.93%. We additionally discuss Markov Regime Switching models as an alternative framework for detecting epidemic transitions. Our findings indicate that these models can generalize to real-world, state-level influenza data and are capable of online/real-time prediction.

Dynamic systems often evolve faster than reliable measurements can be collected. More frequent indirect observations may fill these gaps, but their noise and differing scales complicate estimation of the underlying state. We developed Bayesian Anchored Latent Learning (BALL) to combine sparse reference measurements with denser records on an interpretable scale. A bidirectional transformer teacher reconstructs trajectories from complete training histories, and a forward-only transformer student learns from those reconstructions and observed measurements. Across 30 simulations, BALL reduced composite trajectory error by 7% relative to the same transformer trained directly from measurements, achieving lower error across all datasets. In an applied example using psychiatric records from 1,609 patients, BALL improved the prediction of withheld questionnaire scores compared with direct transformer training at 21- and 28-day measurement schedules. Requests guided by estimated uncertainty further improved prediction. BALL connects retrospective learning with prospective state estimation and provides a framework for directing additional measurement.

Electroencephalography (EEG) preprocessing determines signal quality and interpretation, particularly for transcranial magnetic stimulation combined with EEG (TMS-EEG), where recordings are affected by large and complex stimulation-related artifacts. Several preprocessing approaches have been developed, but substantial variability remains in how pipelines are implemented, documented, and evaluated across recordings, limiting reproducibility and comparability across studies. We developed NESTApp, a MATLAB-based graphical interface built on EEGLAB, to provide an accessible and reproducible framework for implementing and evaluating TMS-EEG preprocessing pipelines. Rather than prescribing a specific pipeline, NESTApp allows users to construct and consistently apply customisable workflows incorporating established EEGLAB and TMS-EEG processing tools, while automatically documenting processing decisions and parameters. Integrated quality-control procedures track data removal and flag recordings based on user-defined criteria, facilitating systematic evaluation across participants. The application also supports group-level visualisation and export of processed TMS-EEG measures for subsequent analyses. Applied to 29 recordings from 16 participants, NESTApp processed 27 and identified those requiring further inspection. By integrating pipeline implementation, documentation, quality control, and group-level evaluation within a single interface, NESTApp provides a transparent framework for TMS-EEG preprocessing that may improve reproducibility, facilitate consistent processing across cohorts, and lower technical barriers to the implementation of established preprocessing approaches.

Tabular synthetic data generation (SDG) can facilitate research and development in the health domain, as access to health data is restricted. To accommodate for its structural complexity, such as multimodal distributions and fragmentation, transformer models provides an alternative to conventional SDG methods since they are better equipped to infer global spatial coherence due to textual context of tabular records. However, methods for optimising their adaption to tabular SDG are still largely unexplored. We contribute to the understanding of transformer-based SDG by evaluating fidelity and privacy of three prompting regimes, zero shot, one shot and few shot training, for tabular health SDG using small transformer models. We evaluated llama 3.2 (1B and 3B parameters) and Phi (1.3B and 2.7B parameters), on a real clinical dataset. Our results showed that zero shot learning was less prone to hallucinations and performed overall better for fidelity, but at the loss of privacy in comparison to the other regimes. Our results showed no differences between model sizes and families. Future studies should extend the analysis to other models and datasets, and explore strategies to reduce hallucinations.

Deep learning models for electroencephalography (EEG) pathology detection achieve competitive accuracy but offer limited interpretability. In this paper, we introduce concept bottleneck models (CBMs) for EEG pathology detection which use clinical EEG biomarkers computed analytically from the signal as a bottleneck to be used for prediction. Those concepts include band power, spectral ratios, alpha peak frequency and amplitude, hemispheric asymmetry and phase locking values. With the backbone based on shallow convolutional neural network (CNN), we compare a black box baseline with two variants of CBMs. The hybrid variant is a classifier receives a residual projection of the backbone features. The pure variant is a CBM where the classifier receives only the predicted concepts. Models are evaluated on abnormality detection and dementia classification followed by concept prediction quality and leakage analysis. Both CBMs approach the baseline on TUAB (82.7-82.9% vs 83.6%) and are 2-5 percentage points lower on CAUEEG (57.9-60.5% vs 62.7%). The pure CBM exhibits concept fidelity concern where the predicted concepts deviate from their ground truth values. Replacing them with their true values causes severe cost on accuracy by 26 and 22 points on TUAB and CAUEEG. The concept fidelity concern is mitigated by increasing the weight of the concept loss to match the ground truth concepts. the mitigation comes with small accuracy cost on TUAB but a relatively larger cost on CAUEEG. The code of the experiments and full logs are available at https://www.github.com/mhmdrdwn/cbm.

Biomarker discovery from high-dimensional RNA sequencing data remains challenging. Conventional methods such as differential expression analysis, pairwise protein-protein interaction networks, and weighted gene co-expression network analysis suffer from false-positive interactions, transitivity-driven noise, and arbitrary thresholds for feature selection. Addressing these limitations, this study proposed a novel framework, Hypergraph Regularised Fuzzy Rough Gene Selection (HR-FRGS), for knowledge-driven biomarker discovery. This pipeline integrates information-rich protein clustering with entropy filtering and PPI-pruned co-expression interactions to form a dual-layer hypergraph. A hypergraph-based scoring method that combines Random Walk with Restart diffusion and Hypergraph Betweenness Centrality is used to identify genes that are central in the biological network. Furthermore an autonomous fuzzy rough set selection eliminates arbitrary threshold dependency for gene selection. HR-FRGS was applied to four TCGA cancer cohorts: Lung Adenocarcinoma, Head and Neck Cancer, Kidney Clear Cell Carcinoma, and Colon Cancer, which reduced over 60,000 transcripts to compact biomarker panels. Validation using classical Machine Learning algorithms with cross-validation demonstrated that biomarker panels matched or exceeded the classification performance of the full transcriptome (AUC > 0.99, MCC > 0.94) and confirmed generalizability (MCC $\geq$ 0.893). Benchmarking against baseline methods and an ablation study showed the contribution of major parts of the algorithm. Functional enrichment analysis captures established pan-cancer hallmarks and cohort-specific oncogenic mechanisms, confirming the biological relevance of the identified genes.

Electrical stimulation of brain activity has emerged as a key therapeutic intervention for neurological diseases. The success of these approaches relies on precisely tuned stimulation parameters. A major challenge is that these parameters should ideally be adjusted in real-time based on changes in brain activity. Closed-loop controllers address this challenge by monitoring brain activity and adapting stimulation according to ongoing changes in neural dynamics. While machine learning has been helpful in this context, closed-loop controllers typically do not adapt in real-time to fluctuations in brain activity. Here, we propose a novel framework based on reservoir computing to train a closed-loop, real-time neural controller. This approach, termed CLEAR-FORCE, trains the output weights of a recurrent network based on a combination of target signals and feedback from brain activity. Two series of simulations were performed, where the controller was successful at (1) inducing neural oscillations in a population of spiking neurons and (2) suppressing pathological oscillations. This framework provides a promising avenue for the implementation of neural controllers in low-powered, real-time, and adaptive hardware that harnesses machine learning for the personalized treatment of brain disorders.

Computer vision approaches to disease motor assessment are limited by clinical video dataset scarcity and distributional imbalance, motivating interest in generative video models as a potential source of training data. We introduce a three-component framework for evaluating the clinical fidelity of synthetic medical motion data, assessing visual fidelity, biomechanical stability, and pathophysiological accuracy, and apply it to videos generated by the text-to-video model Sora 2 depicting Parkinsonian hand-fisting motions across MDSUPDRS severity levels 0-2 (normal to mild-moderate motor impairment). We further use real-versus-real bootstrapping to compare synthetic-real differences against the natural variability of real clinical videos. Although generated videos appear visually realistic, quantitative analysis shows substantial divergence from real clinical recordings, including weaker severity-dependent patterns of bradykinesia and hypokinesia, less realistic tremor rhythms, and substantial temporal instability. These findings reveal a motion-domain gap between Sora-2-generated and real clinical motor behavior in this Parkinsonian hand-motion setting and demonstrate that visual realism alone is insufficient to establish the clinical utility of synthetic video data for training or evaluating medical computer vision systems.

Depression in Alzheimer's disease (AD) is clinically challenging to characterise because affective and cognitive manifestations frequently overlap with the underlying neurodegenerative condition. This study investigates depression-related speech patterns in AD using an explainable multimodal framework that integrates linguistic and acoustic features from elicited picture-description speech. To address the absence of directly observed depression labels in the target AD cohort, we employ a source-informed cross-dataset transfer strategy. Unsupervised clustering identified two distinct speech sub-phenotypes within the AD cohort. By comparing these unsupervised representations to a depression-labelled source corpus, one cluster demonstrated mathematical proximity (measured via cosine similarity in a shared latent space) to the source depression centroid. We explicitly acknowledge that this proximity reflects geometric similarity in a shared latent space, which may encapsulate overlapping domain characteristics alongside affective variance. To validate the structural integrity and separability of these discovered clusters, a proxy supervised classification task was employed. The retained multimodal artificial neural network (ANN) integrated information from both modalities and achieved 92.73\% cluster separability accuracy. This demonstrates that the representation-derived two-cluster partition was highly learnable on the independent internal hold-out test set; it does not establish clinical validity, longitudinal stability, or diagnostic validity of the identified sub-phenotypes. For interpretability, Shapley Additive exPlanations (SHAP) analysis was utilised to extract feature attributions and organise influential acoustic and linguistic features into a multimodal taxonomy. Furthermore, a Multimodal SHAP Attribution Magnitude (MSAM) score was derived as an exploratory model-based attribution score rather than a clinically validated severity measure. Ultimately, this study provides an interpretable computational baseline for characterising depression-related speech variance in AD, establishing a structural foundation for future prospective validation using independently labelled clinical cohorts.

Biomedical artificial intelligence (AI) increasingly relies on heterogeneous data sources, yet differences in data structure, terminology, evidence quality, and provenance complicate their integration into reliable knowledge resources. Here, we develop an evidence-aware framework for processing and integrating heterogeneous pharmacovigilance data from FDA Adverse Event Reporting System (FAERS) reports, biomedical literature, clinical trials, and electronic health records in Mass General Brigham. The framework combines large language model (LLM)-based information extraction, ontology-driven semantic normalization, cross-source evidence assessment, statistical and machine learning-based prioritization, and ingredient-based adverse drug event (ADE) relationship inference to transform heterogeneous evidence into a structured and evidence-based knowledge resource. The constructed knowledge system contains 11,588 drug nodes, 44,843 ingredient nodes, 3,275 ADE nodes, 993 indication nodes, and more than 2.47 million relationships, with each drug-ADE relationship assigned a confidence score. We further developed a drug-level web interface for accessing the knowledge resource and validated its utility in downstream AI tasks. Specifically, incorporating the developed knowledge resource improved the comprehensiveness, relevance, and overall quality of LLM-based drug-specific ADE synthesis and improved the precision and F1 score of clinical ADE relation extraction. These results demonstrate that AI-assisted processing combined with evidence-aware curation can transform heterogeneous biomedical evidence into reusable, AI-ready knowledge with explicit provenance and evidence strength information. The framework provides a general strategy for integrating heterogeneous biomedical data to support reproducible knowledge construction and downstream biomedical AI applications.

Electronic health records provide a source of real-world information for disease risk prediction, but many machine learning models learn implicit associations that are difficult to inspect or use for clinical reasoning. Causal Bayesian networks (CBNs) offer a form of causal-interpretable machine learning by representing conditional dependencies, putative directional relations, and probabilistic evidence propagation in a directed acyclic graph. However, conventional CBN structure learning becomes unstable and computationally expensive when applied to large-scale EHR data. To address this limitation, we propose UPEBNL, a scalable framework for causal-interpretable cancer prescreening based on parallel CBN learning. UPEBNL integrates adaptive data slicing, quality-aware structure aggregation, and global DAG construction to learn stable and interpretable dependency structures from large-scale observational data. We evaluated UPEBNL in high-dimensional and multi-million-sample simulations and applied it to EHR-based prescreening for esophageal and colorectal cancer. In simulations, UPEBNL improved structural recovery accuracy by nearly 40% and achieved up to a 221.28-fold speedup over conventional CBN learning strategies. For cancer risk prediction, the learned CBNs provided interpretable evidence paths and achieved validation AUCs of 0.8171 for esophageal cancer and 0.784 for colorectal cancer. Calibration and decision curve analyses further supported the reliability and clinical utility of the models. These findings suggest that scalable CBN learning can support interpretable cancer prescreening from large-scale EHR data.

Although largely preventable, cardiovascular disease (CVD) is the leading cause of death worldwide. Synthetic data generation (SDG) of health data can facilitate data sharing for research and development of personalised cardiovascular disease prevention tools. Current state-of-the-art SDG methods are limited to cross-sectional data or focused on short-term or in-patient EHR applications lacking benchmarks for generalisability. Since prevention is a long-term longitudinal objective, these limitations must be addressed. We evaluated two tabular generative adversarial networks, TGAN and CTGAN, for privacy and fidelity on a structured 6-year longitudinal trial dataset within CVD prevention. We compared performance with a rudimentary perturbation method. In addition, we performed a variable-wise evaluation and an age-stratified analysis of the higher performing model to assess preservation of clinically relevant characteristics. Overall, CTGAN showed better fidelity than TGAN. The models performed similarly within privacy, showing better results than the perturbation method. CTGAN had lower performance in comparison to the perturbation method within numerical fidelity of continuous variables and overall temporal fidelity. Furthermore, CTGAN's performance was lower for younger age groups than older. CTGAN shows better than or equal performance within fidelity and privacy than TGAN and the perturbation method on a long-term longitudinal dataset within CVD prevention. To the best of our knowledge, this is the first study evaluating CTGAN on a longitudinal dataset and our findings suggest that handling of temporal characteristics and imbalanced subgroups need further refinement.

INTRODUCTION: The digital clock drawing test (dCDT) is a cognitive screening tool capturing high-resolution pen-movement data. Existing approaches for classifying cognitive impairment from dCDTs rely on selected features or image-based methods. We propose representing dCDTs as structural networks to classify cognitive impairment and characterize spatial organization in clock drawings. METHODS: Weighted networks were constructed from 3,362 Framingham Heart Study participants, with and without cognitive impairment. Network representations were generated separately for command and copy conditions, with nodes representing pre-defined clock components (digits, hands, clock face) and edges capturing pairwise spatial relationships between components. Random forest models and graph convolutional networks were trained to predict cognitive impairment from the networks. Models were benchmarked against demographics-only and established summary feature baselines. RESULTS: Network-based models achieved AUC values comparable to the established summary feature baseline across command-only and copy-only conditions. Differences in spatial organization between the cognitively intact and impaired groups were greatest in the upper-right clock region, involving digits 1 and 2, the clock hands, and the surrounding clock face. Differences between the command and copy networks were larger among cognitively impaired participants. DISCUSSION: The proposed network representations provide an objective, scalable, and flexible framework for representing clock drawings for use in classification models. dCDT networks matched the predictive performance of established summary feature-based approaches and identified clock regions where spatial organization differed by cognitive status. After external validation, this approach has the potential to be incorporated within a clinical workflow to support automated and interpretable cognitive screening.

Text-driven medical image segmentation demands unified models based on multi-modal learning, capable of processing diverse imaging modalities while providing spatially reliable prediction estimates for clinical practice. Nevertheless, existing vision-language model solutions suffer from poor domain generalization and exhibit limited capability for uncertainty estimation to model the cumulative unreliability of cross-modal alignment across network layers. In this paper, we propose UniMedSeg, a unified vision-language framework for multi-modal medical image segmentation built upon frozen pre-trained vision-language backbones. Our framework incorporates modality-aware adaptation, cross-layer uncertainty-guided encoding, and a frequency-spatial dual-prompt decoder, wherein the progressive uncertainty propagation mechanism of the encoder suppresses misleading cross-modal features, whereas the decoder disentangles anatomical structure and boundary details in the frequency domain under dual textual prompts. Auxiliary losses further sharpen boundary representations and calibrate pixel-wise uncertainty maps. Extensive experiments demonstrate that UniMedSeg preserves competitive in-domain segmentation performance, improves domain generalization, and yields clinically useful spatial risk estimation.